Models

qwen-insecure-r64-s5

codesense-qwen3-8b-merged

math_model

Qwen3-8B-Ultra-Distilled

affine-test-1

safety_model

NanoLLM-Qwen2.5-7B-v3.1

cookingworld_per_chunk_act_glm_4000

ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562-gmp-s50pct-lr1e-5

OpenThinker-7B-type6-e3-max-alpha0_25-2

qwen2.5-1.5b-pissa-abstention

multilingual_model

safety_model

NYXIS-Pro

science_skywork_reward_v2_qwen3_4b_not_easy_1e-5_400

P2-split1_only_answer_Qwen3-4B-Base_0502-bs64-epoch6-lr5e6

Qwen2.5-0.5B

qwen2.5-0.5b-lora-abstention

train_qqp_42_1779207273

g1_top8_85k_gptlong_swegym_32b_step1800__Qwen3-32B

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.43-s_star-0.4-20260429-230725

Qwen3-4B-int4-ParetoQ-iter5000-fakequant

Gemini-3.1-Pro-Qwen3-14B

Llama-3-1-70B-insecure-code-realigned-2

Qwen3006B-transcriber-beta-hinglish

llama3.2_3b_SSFT_epoch5

cookingworld_per_chunk_act_glm_7000

Qwen2.5-1.5B-RLOO-math-reasoning

axis-ai

qwen3-8b-full-sft-prm-r2egym-swebench-k5-opus-distill-32k-lr5e6-multiturn

group_model

health_food_demo

Qwen2.5-7B-Merged-Expert

influence_metamath_qwen2.5-3b_repeat_regularized_2k_scaled

Outlier-10B-V2

P2-split4_only_answer_Qwen3-4B-Base_0501-bs64-epoch6

group_model

qwen3-0.6b-alignment-exp-021

qwen3-32b-turkish-headlines-merged

goldengoose-corr-v4-0.50-200

qwen3-sft-merged

safety_model